Local And Global Spectral Visual Saliency Estimation Based On Human Visual Behavior
Journal Title: Acta Technica Napocensis- Electronica-Telecomunicatii (Electronics and Telecommunications) - Year 2013, Vol 54, Issue 3
Abstract
In this paper a saliency detection algorithm based on local and global information is proposed. The proposed method extends a previous work by calculating the pixels saliency by means of local patches and the global dissimilarities between a patch and all other patches based on color contrast differences and spatial distances. The image patch scale is fixed and in accordance with the size of the regions of interest (ROI), while the spatial difference takes into account the fact that the focus of attention can subtend a certain region from the visual angle. Resulted algorithm is tested in an image retargeting application and proves its effectiveness.
Authors and Affiliations
Oana Loredana BUZATU
Keywords
Related Articles
- EP ID EP141802
- DOI -
- Views 121
- Downloads 0
Novel Current Line Sensor Based On Matched Optocouplers For Active Power Factor Correction
This paper presents a novel line current sensor which allows safe and accurate data acquisition for power factor measurements: it uses a pair of matched optocouplers arranged so that the difference between their outputs...
Safe Pre-Pass Software Bypassing for Transport Triggered Processors
The Transport Triggered Architecture is an architectural style where the internal transport buses of a processor are exposed in the instruction set. Since software has full control over data transports, data can be direc...
NOAA Signal Decoding And Image Processing Using GNU-Radio
The paper presents several technical issues and software implementations proposed in order to decode, process, and render images received from NOAA satellites. NOAA satellites are seeking extreme weather events on Earth....
An Experimental Architecture For Basic IPTV Concepts Implementation and Testing
The paper describes basic concepts and a practical implementation of a simple architecture for IPTV content creation and distribution. The architecture is conceived to make possible extensive tests. Audio-video content i...
Forecasting By Neural Networks In The Wavelet Domain
This paper presents a forecasting method for time series. This method combines the wavelet analysis and several forecasting techniques such as Artificial Neural Networks (ANN), linear regression and random walk. The prop...